Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    betting over/under totals

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    貸款
    -0.08
    贷款
    -0.07
    阿里
    -0.07
     cocaine
    -0.07
     ست
    -0.07
    银行业
    -0.07
    _jobs
    -0.07
    cox
    -0.07
    来不及
    -0.07
    _videos
    -0.07
    POSITIVE LOGITS
    .gl
    0.08
    filt
    0.07
    뽀
    0.07
    ださい
    0.07
    .hxx
    0.07
    //----------------------------------------------------------------------------↵
    0.07
    𬭩
    0.07
     proprietà
    0.07
    玞
    0.07
    厾
    0.06
    Act Density 0.005%

    No Known Activations